Model profile
Qwen3.5 35B A3B
Evidence summary
Safety. Qwen3.5 35B A3B has an estimated Safety rank of #249; its 90% source-sensitivity interval is #137–#309. Its behavior-only rank is #244; company governance moves the combined estimate to #249. Published Safety evidence spans 5 eval lineages and 4 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #19 of 248); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #219 of 248).
Freedom. Qwen3.5 35B A3B has an estimated Freedom rank of #491; its 90% source-sensitivity interval is #252–#567. Published Freedom evidence spans 3 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #29 of 248); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #228 of 248).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗qwen3-5-35b-a3b
- Hugging Face ↗Qwen/Qwen3.5-35B-A3B
- OpenRouter ↗qwen/qwen3.5-35b-a3b
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
Finetunes
Direct finetunes linked to this canonical base model. Quantized and repackaged derivatives are excluded.
- 91chenxs/Huihui-Qwen3.5-35B-A3B-abliterated ↗Direct non-quantized finetune documented by Hugging Face metadata
huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated ↗Direct non-quantized finetune documented by Hugging Face metadata
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #218 / 345 | ↓0.8543 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #75 / 111 | ↑1425.0 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #57 / 248 | ↑26.61 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #219 / 248 | ↑73.17 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #19 / 248 | ↑98.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #55 / 246 | ↑98.36 | Source ↗official | |
| SABERoverall_safety_rate | #10 / 13 | ↑22.73 | Source ↗official | |
| SABERscenario_a_safety_rate | #11 / 13 | ↑23.55 | Source ↗official | |
| SABERscenario_b_safety_rate | #7 / 13 | ↑32.73 | Source ↗official | |
| SABERscenario_c_safety_rate | #8 / 13 | ↑14.54 | Source ↗official | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #56 / 94 | ↑89.5 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #29 / 248 | ↓73.17 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #228 / 248 | ↓98.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #190 / 246 | ↓98.36 | Source ↗official | |
| SpeechMap model completioncomplete_pct | #130 / 181 | ↑44.3 | Source ↗official | |
| UGI Leaderboard — base-model willingnesswillingness_adherence_score | #79 / 156 | ↑1.5 | Source ↗official | |
| UGI Leaderboard — base-model willingnesswillingness_direct_score | #66 / 156 | ↑3.5 | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.